INDEX

Explanations

words related to turning or rotating

oai_token-act-pair · gpt-3.5-turbo

instances and variations of the word "spin"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Cla

-0.75

 Antioch

-0.71

WHERE

-0.67

Lv

-0.65

EMA

-0.65

ODY

-0.64

eson

-0.63

"},"

-0.62

hurst

-0.62

artment

-0.61

POSITIVE LOGITS

 spin

3.95

spin

2.71

 spins

2.47

 Spin

2.35

 spun

2.19

 spinning

2.03

 twist

1.44

 twists

1.20

 weave

1.04

 reboot

1.03

Activations Density 0.024%

words related to turning or rotating

instances and variations of the word "spin"

No Comments

No Known Activations